# Prehistoriq

> Prehistoriq is building multi-model code review for code written by agents. Code review is broken: too much to read, too little to trust, nothing to learn from.

Still reviewing code by hand? So prehistoriq.

## The problem

You used to learn by reading your teammates' code. Now the code is written by prompts, skills and loops you never see. Was it checked? Was it vibecoded? The diff can't tell you.

## What Prehistoriq is building: review that keeps up

- Trust what ships: each change shows that it runs, and whether it broke something nobody looked at.
- Read only what needs you: the agent that wrote the code wants it merged. Other models review it first and tell you where to look.
- Learn how it was built: the prompts, skills and loops behind a change sit next to the code, so your team can learn from them.

Prehistoriq is building the human's seat in AI-speed development, with its first teams. The waitlist is on the homepage.

## Pages

- [Prehistoriq](https://www.prehistoriq.com/): what Prehistoriq is building, and the waitlist.
- [Stacks: how engineers actually use coding agents](https://www.prehistoriq.com/stacks/llms.txt): 94 sourced setups, open data.

## Elsewhere

- [@PrehistoriqHQ on X](https://x.com/PrehistoriqHQ)
- [Stacks data on GitHub](https://github.com/prehistoriq/stacks)